Log In Sign Up

A Transformer-based Framework for Multivariate Time Series Representation Learning

by   George Zerveas, et al.

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and classification, forecasting and missing value imputation. By evaluating our models on several benchmark datasets for multivariate time series regression and classification, we show that not only does our modeling approach represent the most successful method employing unsupervised learning of multivariate time series presented to date, but also that it exceeds the current state-of-the-art performance of supervised methods; it does so even when the number of training samples is very limited, while offering computational efficiency. Finally, we demonstrate that unsupervised pre-training of our transformer models offers a substantial performance benefit over fully supervised learning, even without leveraging additional unlabeled data, i.e., by reusing the same data samples through the unsupervised objective.


page 1

page 2

page 3

page 4


MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting

Large-scale self-supervised pre-training Transformer architecture have s...

Improving Clinical Predictions through Unsupervised Time Series Representation Learning

In this work, we investigate unsupervised representation learning on med...

Self-supervised Transformer for Multivariate Clinical Time-Series with Missing Values

Multivariate time-series (MVTS) data are frequently observed in critical...

Enhancing Transformer Efficiency for Multivariate Time Series Classification

Most current multivariate time series (MTS) classification algorithms fo...

DBT-DMAE: An Effective Multivariate Time Series Pre-Train Model under Missing Data

Multivariate time series(MTS) is a universal data type related to many p...

Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization

We propose a new model based on the deconvolutional networks and SAX dis...

Code Repositories


Multivariate Time Series Transformer, public version

view repo


Multivariate time series representation learning (using bert-like model adapted for TS)

view repo



view repo